STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6 Sol vs Step 5 Preview

GPT-6 Sol leads Step 5 Preview by 12.7 points on StealthMark, 51.7 to 39.0. It leads on 8 of 9 benchmarks, including both games, and Step 5 Preview on 1. GPT-6 Sol scores higher on Beach, with its largest category advantage in anatomy & construction.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

51.7/100Overall rank 13/53
39.0/100Overall rank 36/53

General Intelligence

46.1/100
37.1/100

Visual Intelligence

61.6/100
41.9/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

  • GPT-6 Sol

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6 Sol
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.05M tokens of context.

  • GPT-6 Sol
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6 Sol: $10$2 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
GPT-6 Sol: 1.05MTied128K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
GPT-6 Sol: 91tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
GPT-6 Sol: Not disclosedStep 5 Preview: 600B27B active
Developer
OpenAIStepFun
Released
22 Sep 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textText, image, video → text
Architecture
Not publishedSparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceGPT-6 Sol ↗Step 5 Preview ↗

Anticipating threats and planning ahead. Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

GPT-6 Sol 30.4/100Rank 28/49

Survived 0 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 20

Step 5 Preview 59.9/100Rank 42/491 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelGPT-6 SolStep 5 Preview
Level 1Second Thoughts
17 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
5 ptsOut of lives
Pending
Level 3Hide or Flight
6 ptsOut of lives
Pending

Cooperative planning and learning from experience. Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

GPT-6 Sol 76.6/100Rank 12/50

Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Step 5 Preview 40.7/100Rank 28/50

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelGPT-6 SolStep 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
9 ptsCleared
Level 3Relay vault
18.4 ptsCleared
18.6 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
15 ptsFinished early

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

GPT-6 Sol

The centered sphere, separate airborne black form and color ordering support scene recognition. Rounded shading and curved rims provide readable volume and gloss. Shrinking side images, a floor counterpart and curved lamp highlights provide isolated reflection cues, but broad bands and sparse repetitions leave nested room imagery, outer chains and ordered emitter mapping unsupported. Vertical framing departs from the prescribed view, while paint contact, transport and solid-metal appearance remain weak or uncertain.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
State at 600 ms19.0/2520.0/25
Camera and placement12.0/1513.5/15
Reflections8.0/12020.0/120
Materials and scale6.5/107.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

GPT-6 Sol

Six evenly spaced lobes, small outward-facing heads and a regular hexagonal opening make the motif immediately readable. The central angular band merges several intersections, weakening the alternating weave. Pale shading gives modest volume, but scales are sparse and repetitive, crossing shadows are weak, and the heads have limited anatomical definition.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
Task & likeness7.5/106.0/10
Anatomy & construction6.5/104.5/10
Space & placement6.5/105.0/10
Light & reflections6.0/105.5/10
Purposeful detail6.5/105.5/10
Artistry & character7.0/105.0/10
Materials & effects5.5/106.0/10
Visual integrity6.0/105.0/10

Benchmark task

GPT-6 Sol

A pale serpent woven into an interlocking knot tests connected anatomy, repeated structure and readable overlaps. Organic surface detail must work with the overall geometry.

Step 5 Preview

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6 Sol

The dark clothing, crossed arms, restrained smile and distant landscape establish the Mona Lisa reference. Replication is limited by the oversized, nearly frontal head, schematic eyes and fingerless hand shapes. Soft shading suggests facial volume, but muddy transitions and angular scenery weaken depth and painterly finish.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
Task & likeness5.5/104.0/10
Anatomy & construction3.5/104.0/10
Space & placement5.5/104.0/10
Light & reflections6.0/103.5/10
Purposeful detail4.5/104.0/10
Artistry & character5.0/104.0/10
Materials & effects4.5/103.0/10
Visual integrity6.0/103.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

GPT-6 Sol

A cohesive, appealing beach illustration with framing palms, a warm sunset and a clear reflection path. The turtle, crab, birds and beach ball fulfill the playful brief. Clean silhouettes and restrained colors work well, while simplified anatomy, shallow spatial cues and inconsistent foreground shadows limit depth and finish.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
Task & likeness8.5/104.0/10
Anatomy & construction7.0/103.0/10
Space & placement7.0/103.5/10
Light & reflections6.5/103.5/10
Purposeful detail7.0/103.0/10
Artistry & character6.0/103.0/10
Materials & effects6.5/103.5/10
Visual integrity7.5/104.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

The judgment

GPT-6 Sol

This benchmark has not been assessed yet.

Step 5 Preview

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Same task instructions

Scene composition and interacting subjects.

The judgment

GPT-6 Sol

The raccoon rides the dog's back, and the dog's connected foreleg reaches the steering grip. Expressive faces, a cohesive palette and sweeping wake make an appealing illustration. Vehicle construction and seating remain simplified; broad splash ribbons convey speed more convincingly than physical displacement. The sun has little corresponding reflection or effect on the subjects.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
Task & likeness7.5/104.0/10
Anatomy & construction6.5/104.5/10
Space & placement7.5/103.0/10
Light & reflections6.0/103.5/10
Purposeful detail7.5/104.0/10
Artistry & character6.5/103.5/10
Materials & effects7.5/103.0/10
Visual integrity8.0/103.0/10

Benchmark task

A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.

Pelican

Same task instructions

Subject construction and spatial relationships.

The judgment

GPT-6 Sol

The pelican reads clearly, with an expressive face, generous bill and appealing pastel composition. Spokes, basket weave and feather contours are carefully organized. Both legs connect to the body, though joint definition and pedal contacts are simplified. Consistent wheel placement and a ground shadow establish support; restrained shading gives limited volume.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryGPT-6 SolStep 5 Preview
Task & likeness9.0/103.0/10
Anatomy & construction7.5/103.0/10
Space & placement8.0/103.0/10
Light & reflections7.0/103.0/10
Purposeful detail8.0/104.0/10
Artistry & character8.5/103.0/10
Materials & effects7.0/103.0/10
Visual integrity8.5/102.0/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.